Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 192 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.0525. Min Range: -4.0525

Max Act: 4.0525. Min Act: -0.1700

Data Index: 3041724 (Open Web Text)

Max Activating Token Index: 943

Text #1

Max Range: 4.0525. Min Range: -4.0525

Max Act: 4.0391. Min Act: -0.1700

Data Index: 911367 (Open Web Text)

Max Activating Token Index: 554

Text #2

Max Range: 4.0525. Min Range: -4.0525

Max Act: 4.0130. Min Act: -0.1700

Data Index: 7527166 (Open Web Text)

Max Activating Token Index: 963

Text #3

Max Range: 4.0525. Min Range: -4.0525

Max Act: 4.0078. Min Act: -0.1700

Data Index: 5562346 (Open Web Text)

Max Activating Token Index: 333

Text #4

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.9474. Min Act: -0.1700

Data Index: 5685163 (Open Web Text)

Max Activating Token Index: 536

Text #5

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.9620. Min Act: -0.1700

Data Index: 7633149 (Open Web Text)

Max Activating Token Index: 718

Text #6

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.9111. Min Act: -0.1700

Data Index: 6840216 (Open Web Text)

Max Activating Token Index: 88

Text #7

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.9379. Min Act: -0.1700

Data Index: 463426 (Open Web Text)

Max Activating Token Index: 1014

Text #8

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.9337. Min Act: -0.1700

Data Index: 8233802 (Open Web Text)

Max Activating Token Index: 527

Text #9

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.9184. Min Act: -0.1700

Data Index: 1275410 (Open Web Text)

Max Activating Token Index: 459

Text #10

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.9014. Min Act: -0.1700

Data Index: 2606990 (Open Web Text)

Max Activating Token Index: 486

Text #11

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.9333. Min Act: -0.1700

Data Index: 7941606 (Open Web Text)

Max Activating Token Index: 591

Text #12

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.9248. Min Act: -0.1700

Data Index: 1119115 (Open Web Text)

Max Activating Token Index: 429

Text #13

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.9088. Min Act: -0.1700

Data Index: 2066594 (Open Web Text)

Max Activating Token Index: 430

Text #14

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.9023. Min Act: -0.1700

Data Index: 7257709 (Open Web Text)

Max Activating Token Index: 142

Text #15

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.9105. Min Act: -0.1700

Data Index: 6142020 (Open Web Text)

Max Activating Token Index: 447

Text #16

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8949. Min Act: -0.1700

Data Index: 5442051 (Open Web Text)

Max Activating Token Index: 520

Text #17

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8761. Min Act: -0.1700

Data Index: 3228926 (Open Web Text)

Max Activating Token Index: 951

Text #18

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.8796. Min Act: -0.1700

Data Index: 5908416 (Open Web Text)

Max Activating Token Index: 975

Text #19

Max Range: 4.0525. Min Range: -4.0525

Max Act: 3.9174. Min Act: -0.1700

Data Index: 1331369 (Open Web Text)

Max Activating Token Index: 945